INDEX

Explanations

instances of the word "so"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

so

-0.25

 ÑĤÐ°Ðº

-0.19

å¦ĤæŃ¤

-0.18

 sÃ¥

-0.17

ContentLoaded

-0.16

ponent

-0.16

pane

-0.15

 cosÃ¬

-0.14

ussen

-0.14

ril

-0.14

POSITIVE LOGITS

-called

0.42

far

0.31

iled

0.27

aks

0.26

jour

0.26

ething

0.25

oner

0.25

oth

0.25

 much

0.23

apy

0.23

Activations Density 0.155%

instances of the word "so"

No Comments

No Known Activations